{
  "slug": "mimir",
  "term": "MIMIR",
  "aliases": [
    "MIMIR cache profiler"
  ],
  "definition": "MIMIR is an online cache profiler that estimates hit-ratio curves by grouping recency information into buckets.",
  "note": "Bucketed recency estimates trade precision for lower profiling cost. Ghost identifiers or counting Bloom filters extend the estimated curve beyond resident capacity; a ghost match still requires fetching the payload. Filter false positives can distort predictions. [paper]\n\nThe distributed construction assumes uniform random placement and equal per-server capacity. It is not an optimizer over arbitrary capacity splits. Compatible request ratios must pool hit and request counts, rather than average percentages. [paper] [ratios]\n\nConstructed cold-start LRU example: server A alternates two keys for 90 requests; B repeats one key for 10. One slot each gives 0 + 9 hits out of 100 (9%), not the unweighted 45%. Giving both slots to A yields 88/100 (88%) with routing unchanged. This is illustrative trace arithmetic, not a MIMIR reproduction. [example]\n\nIn the paper, curve accuracy is 1 minus mean absolute error across tested capacities. It is neither hit ratio nor a worst-capacity error bound. Two constructed 100-point curves can agree at 99 capacities yet differ by 100 percentage points at the last: 99% accuracy under that metric. [paper] [example]",
  "status": "research",
  "advantages": [],
  "limitations": [
    {
      "text": "The basic model counts equal-size objects; byte-weighted extensions change the measurement unit. An estimated cache curve does not determine backend latency.",
      "citationIds": [
        "paper"
      ]
    }
  ],
  "supersedes": [],
  "supersededBy": [],
  "firstSeen": null,
  "lastSeen": null,
  "updated": "2026-11-19",
  "related": [
    "miss-ratio-curve",
    "ghost-cache-entry",
    "request-hit-ratio",
    "lru-replacement"
  ],
  "citations": [
    {
      "id": "paper",
      "title": "Saemundsson et al. Dynamic Performance Profiling of Cloud Caches. SoCC 2014, sections 2.3-2.5, 3.7 and 4. DOI: 10.1145/2670979.2671007.",
      "url": "https://ymsir.com/papers/mimir-socc.pdf",
      "accessed": "2026-11-19"
    },
    {
      "id": "ratios",
      "title": "Prometheus. Recording rules: aggregate numerator and denominator separately before division.",
      "url": "https://prometheus.io/docs/practices/rules/#aggregation",
      "accessed": "2026-11-19"
    },
    {
      "id": "example",
      "title": "Hesela. Constructed LRU allocation and mean-versus-maximum curve-error controls.",
      "url": "https://hesela.dev/research/mimir/evidence.json",
      "accessed": "2026-11-19"
    },
    {
      "id": "code",
      "title": "Hesela. Exact cold-start LRU replay and curve-error arithmetic; no MIMIR algorithm implementation.",
      "url": "https://hesela.dev/research/mimir/model.mjs",
      "accessed": "2026-11-19"
    },
    {
      "id": "tests",
      "title": "Hesela. Exhaustive small-trace oracle, counter validation and curve-error regression tests.",
      "url": "https://hesela.dev/research/mimir/model.test.mjs",
      "accessed": "2026-11-19"
    },
    {
      "id": "observatory",
      "title": "Hesela. Cache sizing, workload boundaries and hit-ratio accounting.",
      "url": "https://hesela.com/analyses/ssd-mapping-cache-hmb/#hit-ratio-accounting",
      "accessed": "2026-11-19"
    }
  ],
  "provenance": [
    "The author-hosted 14-page SoCC 2014 paper was read beyond its abstract. Historical performance figures are not present-day guarantees.",
    "The examples use synthetic requests and constructed curves. They test interpretation, not MIMIR fidelity, concurrency or measured device performance."
  ]
}
